Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@zentao-rest-v1-mcp Show all my pending tasks"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
面向禅道开源版的 MCP 服务。优先使用 REST v1，只有明确的 REST v1 路由不兼容时才回退 Legacy Session API。
支持禅道 REST v1 Token 认证。
支持任务、Bug、需求、测试用例和测试单的查询与操作。
支持创建任务、更新任务、开始任务、完成任务、关闭任务和解决 Bug。
写入操作遵循“写入一次、写后回读”，避免重复提交。
读取接口在明确不兼容时回退 Legacy；认证失败、参数错误和写入结果不明时不自动切换通道。
支持 ZENTAO_TIMEOUT_MS 和 ZENTAO_SESSION_TTL_MS 配置。
Related MCP server: ZenTao MCP Server
Node.js >=18.0.0
禅道开源版实例，已启用对应 REST API 能力
npm install -g zentao-rest-v1-mcp{
"mcpServers": {
"zentao-rest-v1": {
"command": "zentao-rest-v1-mcp",
"args": [],
"env": {
"ZENTAO_URL": "https://your-zentao.example/zentao",
"ZENTAO_USERNAME": "your-account",
"ZENTAO_PASSWORD": "your-password",
"ZENTAO_TIMEOUT_MS": "30000",
"ZENTAO_SESSION_TTL_MS": "3000000"
}
}
}
}也可以直接运行本地构建产物：
node dist/index.js读取：getBugDetail、getTaskDetail、getMyBugs、getMyTasks、getStoryDetail
任务：createTask、updateTask、startTask、finishTask、closeTask
Bug：updateBug、resolveBug
测试：createTestCase、runTestCase
任务完成流程必须遵循：
wait → startTask → doing → finishTask → done → closeTask → closed完成任务时必须提交实际开始时间 realStarted 和不早于它的实际完成时间 finishedDate，不能只提交日期。
pnpm install --frozen-lockfile
pnpm run build
pnpm run test:smokeZENTAO_URL：禅道站点地址，通常包含 /zentao 部署路径。
ZENTAO_USERNAME：禅道账号。
ZENTAO_PASSWORD：禅道密码，仅通过环境变量传入，不写入源码和日志。
ZENTAO_TIMEOUT_MS：请求超时时间，默认 30000 毫秒。
ZENTAO_SESSION_TTL_MS：Token 本地缓存时间，默认 3000000 毫秒。
MIT。原始 Legacy MCP 实现及其许可证声明保留在本包中。
Inputs: bugId (required).
Inputs: storyId (required).
Inputs: taskId (required).
Inputs: bugIds (required), resolution (required).
Inputs: update (required), taskIds (required).
Inputs: taskId (required), comment.
Inputs: name (required), type (required), executionId (required), pri, +8 more.
Inputs: bugId (required), desc, estimate, taskName, +1 more.
Inputs: storyId (required), taskName (required), desc, estimate, +1 more.
Inputs: testCase (required).
Inputs: bugId (required), exportPath (required).
Inputs: type (required), exportPath (required), id, url, +8 more.
Inputs: url (required), exportPath (required).
Inputs: exportPath (required), limit, status, endDate, +4 more.
Inputs: storyId (required), exportPath (required).
Inputs: taskId (required), update.
Inputs: taskId (required).
Inputs: bugId (required), format.
Inputs: storyId (required).
Inputs: entityId (required), entityType (required).
Inputs: storyId (required), format.
Inputs: bugId (required).
Inputs: bugId (required), downloadImages.
Inputs: bugId (required).
Inputs: no named parameters.
Inputs: entityId (required), entityType (required), format.
Inputs: url (required), exportPath (required).
Inputs: status, productId.
Inputs: no named parameters.
Inputs: status.
Inputs: no named parameters.
Inputs: entityId (required), entityType (required).
Inputs: productId (required), status, moduleId.
Inputs: no named parameters.
Inputs: productId (required), status, moduleId.
Inputs: productId (required), status, moduleId.
Inputs: storyId (required), downloadImages.
Inputs: storyId (required).
Inputs: storyId (required).
Inputs: taskId (required).
Inputs: caseId (required).
Inputs: taskId (required).
Inputs: taskId (required).
Inputs: productId.
Inputs: no named parameters.
Inputs: bugId (required), resolution (required).
Inputs: taskId (required), testRun (required).
Inputs: keyword (required), limit, status, endDate, +3 more.
Inputs: keyword (required), productName (required), limit, status.
Inputs: taskId (required), update (required).
Inputs: bugId (required), update (required).
Inputs: taskId (required), update (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 52 tools
Most tools have fairly clear resource/action targets, but several overlap conceptually: multiple export tools, multiple get-task/get-bug variants, and generic helpers like initZentao/getConfig are easy to confuse. Without descriptions, an agent could struggle to choose between related tools like exportItems, exportModuleItemsAsMarkdown, and exportStoriesBySearch.
The tools mostly follow a camelCase verb_noun pattern such as getTaskDetail, createTestCase, and resolveBug. Minor inconsistencies exist in singular/plural usage and entity-relationship naming, e.g. getStoryRelatedBugs vs getBugRelatedStory, but the overall convention is predictable and readable.
With 52 tools, the surface is far too large for an MCP server, exceeding the 50+ threshold for an extreme mismatch. Many tools are auxiliary helpers, export variants, and analysis/generation utilities that inflate the set beyond a focused CRUD interface. This will overwhelm agents and make tool selection expensive and error-prone.
Task and bug lifecycles are reasonably covered with create, read, update, and state transitions, while test cases and stories have meaningful read/run/export support. However, there are notable gaps: no story update/create/delete, no test case update/delete, and no product detail or project management tools. The presence of many generate/analyze/format helpers does not fully compensate for missing core lifecycle operations.
Search and read Zammad tickets, customers and organizations; add notes, replies and ticket updates.
Read and update tickets, deals, tasks, and contacts in 18 Cores Tracker.
Manage ONES projects, issues, tests, work hours, and Wiki knowledge.
Read and edit your Tasks boards: create and update tasks, comment, and track time.